© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3358
    Prev
    Next
    INDEX
    Explanations

    plural noun categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mit
    -0.08
    MIT
    -0.08
    /Common
    -0.07
    stime
    -0.07
    uid
    -0.07
    bout
    -0.07
    ROC
    -0.07
    lite
    -0.07
    idis
    -0.07
    -required
    -0.07
    POSITIVE LOGITS
    emos
    0.11
     involving
    0.10
     accr
    0.10
     abound
    0.10
     like
    0.10
     flo
    0.09
    âĢİ
    0.09
    worthy
    0.09
    -wise
    0.09
    /pay
    0.09
    Activations Density 0.486%

    No Known Activations